Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f67801ebb648c7be1659c76c13e69088b0d479cc44016ecdbca373282c077b
+oid sha256:333016245037c02fd0259e2943318ecb84f15fc4acbd3c4468b4bca34f3a2f2b
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1d3c3c3a9ac27b433eaffac0fe479b3da4d0e890cd2b2004a97c30b717d0a7
+oid sha256:1fc314f2880a5b29f2d6ef45faa29ad070c0d8ec542672d55536c42391eae74f
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
+oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013652809065465218,
+  "epoch": 0.0020479213598197828,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 46.0,
       "step": 18
+    },
+    {
+      "epoch": 0.0014335449518738481,
+      "grad_norm": 2.6326768420403823e-05,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 46.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016383370878558263,
+      "grad_norm": 1.5010924471425824e-05,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 46.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016383370878558263,
+      "eval_loss": 11.5,
+      "eval_runtime": 36.8458,
+      "eval_samples_per_second": 167.4,
+      "eval_steps_per_second": 83.7,
+      "step": 24
+    },
+    {
+      "epoch": 0.0018431292238378046,
+      "grad_norm": 2.5682602426968515e-05,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0020479213598197828,
+      "grad_norm": 2.1994239432387985e-05,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 847791882240.0,
+  "total_flos": 1246752768000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null